library(dplyr)
library(tidyr)
library(ggplot2)
library(purrr)
library(ordinal)
library(dagitty)
library(broom)
library(gganimate)
library(cowplot)
library(multiverse)
knit_as_emar()

Abstract

In this paper, we investigate the relationship between social media usage in adolescents and depression, using a multiverse analysis [@Steegen2016]. Our findings suggest that the relationship is inconclusive, as the effect of social media usage regressed on self-reported ratings of depression appears to be possibly both positive and negative, depending on arbitrary choices in the data analysis process.

Introduction

With the growing use of digital technology use, especially by younger, impressionable individuals, its impact on their well-being is of growing concern. Recent work has suggested that there may be an small, negative association between digital technology use and adolescent well-being [@Orben2019]. In this work, we focus specifically on usage of social media and its potential impact on mental well-being. Frequent social media usage can expose adolescents to toxic content, which is abundant on online platforms [@Vogel2021]. For example, Instagram has many posts with ``pro-eating disorder’’ content which it has struggled to moderate [@Chancellor2016, @Chancellor2016].

To better assess the harms of social media usage on adolescents, we conduct a survey with N = 300 participants and investigate the association between social media usage and depression using a multiverse analysis. We report our findings below.

Data

Our survey questionnaire consists of 10 items which includes the following:

social_media = readRDS("../../mvis/data/social_media.rds")
head(social_media)
## # A tibble: 6 × 11
##     .id parent_i…¹   age sibli…² has_s…³ depre…⁴ physi…⁵    I1    I2    I3    I4
##   <int>      <dbl> <dbl>   <dbl>   <dbl>   <dbl>   <dbl> <dbl> <dbl> <dbl> <dbl>
## 1     1      99000    14      12       1       4       4    19     3   116     2
## 2     2     101000    14      14       1       4       2    15     2    93     2
## 3     3      88000    13      13       1       2       4    15     3    52     1
## 4     4      83000    15      13       1       3       4    21     4    74     1
## 5     5      99000    14      14       1       4       4    20     4   108     4
## 6     6      63000    14      12       1       2       7    12     2    63     3
## # … with abbreviated variable names ¹​parent_income, ²​sibling_age,
## #   ³​has_siblings, ⁴​depression, ⁵​physical_activity
M = multiverse()

Analysis

We plan to use a linear regression model with depression as the dependent variables.

Exclusion criteria

As the data was collected through a survey, we may expect there to be some outliers. We consider four alternatives for outlier_exclusion : - analysing all cases (no exclusion) - cutting off values which are 2.5 SD from the mean - cutting off values which are 3.5 SD from the mean - cutting off values based on Tukey’s fences (first and third quartiles \(\pm\) 1.5 times the interquartile range)

The results in the current analysis reflect

df = social_media
IQR.I1 = quantile(df$I1, probs = 0.75) - quantile(df$I1, probs = 0.25)
IQR.I2 = quantile(df$I2, probs = 0.75) - quantile(df$I2, probs = 0.25)
IQR.I3 = quantile(df$I3, probs = 0.75) - quantile(df$I3, probs = 0.25)
IQR.I4 = quantile(df$I4, probs = 0.75) - quantile(df$I4, probs = 0.25)
df = df %>%
    filter(TRUE) %>%
    mutate(I1 = scale(I1), I2 = scale(I2), I3 = scale(I3), I4 = scale(I4), )
df = social_media
IQR.I1 = quantile(df$I1, probs = 0.75) - quantile(df$I1, probs = 0.25)
IQR.I2 = quantile(df$I2, probs = 0.75) - quantile(df$I2, probs = 0.25)
IQR.I3 = quantile(df$I3, probs = 0.75) - quantile(df$I3, probs = 0.25)
IQR.I4 = quantile(df$I4, probs = 0.75) - quantile(df$I4, probs = 0.25)
df = df %>%
    filter((((I1 >= (quantile(I1, probs = 0.25) - 1.5 * IQR.I1)) & (I1 < (quantile(I1,
        probs = 0.75) + 1.5 * IQR.I1))) & ((I2 >= (quantile(I2, probs = 0.25) - 1.5 *
        IQR.I2)) & (I2 < (quantile(I2, probs = 0.75) + 1.5 * IQR.I2))) & ((I3 >=
        (quantile(I3, probs = 0.25) - 1.5 * IQR.I3)) & (I3 < (quantile(I3, probs = 0.75) +
        1.5 * IQR.I3))) & ((I4 >= (quantile(I4, probs = 0.25) - 1.5 * IQR.I4)) &
        (I4 < (quantile(I4, probs = 0.75) + 1.5 * IQR.I4))))) %>%
    mutate(I1 = scale(I1), I2 = scale(I2), I3 = scale(I3), I4 = scale(I4), )
df = social_media
IQR.I1 = quantile(df$I1, probs = 0.75) - quantile(df$I1, probs = 0.25)
IQR.I2 = quantile(df$I2, probs = 0.75) - quantile(df$I2, probs = 0.25)
IQR.I3 = quantile(df$I3, probs = 0.75) - quantile(df$I3, probs = 0.25)
IQR.I4 = quantile(df$I4, probs = 0.75) - quantile(df$I4, probs = 0.25)
df = df %>%
    filter((((I1 > (mean(I1) - 2.5 * sd(I1))) & (I1 < (mean(I1) + 2.5 * sd(I1)))) &
        ((I2 > (mean(I2) - 2.5 * sd(I2))) & (I2 < (mean(I2) + 2.5 * sd(I2)))) & ((I3 >
        (mean(I3) - 2.5 * sd(I3))) & (I3 < (mean(I3) + 2.5 * sd(I3)))) & ((I4 > (mean(I4) -
        2.5 * sd(I4))) & (I4 < (mean(I4) + 2.5 * sd(I4)))))) %>%
    mutate(I1 = scale(I1), I2 = scale(I2), I3 = scale(I3), I4 = scale(I4), )
df = social_media
IQR.I1 = quantile(df$I1, probs = 0.75) - quantile(df$I1, probs = 0.25)
IQR.I2 = quantile(df$I2, probs = 0.75) - quantile(df$I2, probs = 0.25)
IQR.I3 = quantile(df$I3, probs = 0.75) - quantile(df$I3, probs = 0.25)
IQR.I4 = quantile(df$I4, probs = 0.75) - quantile(df$I4, probs = 0.25)
df = df %>%
    filter((((I1 > (mean(I1) - 3.5 * sd(I1))) & (I1 < (mean(I1) + 3.5 * sd(I1)))) &
        ((I2 > (mean(I2) - 3.5 * sd(I2))) & (I2 < (mean(I2) + 3.5 * sd(I2)))) & ((I3 >
        (mean(I3) - 3.5 * sd(I3))) & (I3 < (mean(I3) + 3.5 * sd(I3)))) & ((I4 > (mean(I4) -
        3.5 * sd(I4))) & (I4 < (mean(I4) + 3.5 * sd(I4)))))) %>%
    mutate(I1 = scale(I1), I2 = scale(I2), I3 = scale(I3), I4 = scale(I4), )
df = social_media

IQR.I1 = quantile(df$I1, probs = 0.75) - quantile(df$I1, probs = 0.25)
IQR.I2 = quantile(df$I2, probs = 0.75) - quantile(df$I2, probs = 0.25)
IQR.I3 = quantile(df$I3, probs = 0.75) - quantile(df$I3, probs = 0.25)
IQR.I4 = quantile(df$I4, probs = 0.75) - quantile(df$I4, probs = 0.25)

df = df %>%
  filter(branch(
    outlier_exclusion,
    "no_exclusion" ~ TRUE,
    "one-half_interquartile_range" ~ (
      ((I1 >= (quantile(I1, probs = 0.25) - 1.5 * IQR.I1)) & (I1 < (quantile(I1, probs = 0.75) + 1.5*IQR.I1))) &
      ((I2 >= (quantile(I2, probs = 0.25) - 1.5 * IQR.I2)) & (I2 < (quantile(I2, probs = 0.75) + 1.5*IQR.I2))) &
      ((I3 >= (quantile(I3, probs = 0.25) - 1.5 * IQR.I3)) & (I3 < (quantile(I3, probs = 0.75) + 1.5*IQR.I3))) &
      ((I4 >= (quantile(I4, probs = 0.25) - 1.5 * IQR.I4)) & (I4 < (quantile(I4, probs = 0.75) + 1.5*IQR.I4)))
    ),
    "two-half_sd_from_mean" ~ (
      ((I1 > (mean(I1) - 2.5 * sd(I1))) & (I1 < (mean(I1) + 2.5 * sd(I1)))) &
      ((I2 > (mean(I2) - 2.5 * sd(I2))) & (I2 < (mean(I2) + 2.5 * sd(I2)))) &
      ((I3 > (mean(I3) - 2.5 * sd(I3))) & (I3 < (mean(I3) + 2.5 * sd(I3)))) &
      ((I4 > (mean(I4) - 2.5 * sd(I4))) & (I4 < (mean(I4) + 2.5 * sd(I4))))
    ),
    "three-half_sd_from_mean" ~ (
      ((I1 > (mean(I1) - 3.5 * sd(I1))) & (I1 < (mean(I1) + 3.5 * sd(I1)))) &
      ((I2 > (mean(I2) - 3.5 * sd(I2))) & (I2 < (mean(I2) + 3.5 * sd(I2)))) &
      ((I3 > (mean(I3) - 3.5 * sd(I3))) & (I3 < (mean(I3) + 3.5 * sd(I3)))) &
      ((I4 > (mean(I4) - 3.5 * sd(I4))) & (I4 < (mean(I4) + 3.5 * sd(I4))))
    )
  )) %>%
  mutate(
    I1 = scale(I1),
    I2 = scale(I2),
    I3 = scale(I3),
    I4 = scale(I4),
  )

Operationalising social media usage

As we have four measures of social media usage, we can use each measure individually, or any possible combination of the four. However, we observe that the measures I3 and I4 are not as strongly correlated with depression as compared to the measures I1 and I2. As such we only consider to composite measures: I1+I2 and I1+I2+I3+I4. Thus, we include six operationalisations of

df = df %>%
    mutate(social_media_usage = I1)
df = df %>%
    mutate(social_media_usage = I2)
df = df %>%
    mutate(social_media_usage = I3)
df = df %>%
    mutate(social_media_usage = I4)
df = df %>%
    mutate(social_media_usage = I1 + I2)
df = df %>%
    mutate(social_media_usage = I1 + I2 + I3 + I4)
df = df %>%
    mutate(social_media_usage = I1)
df = df %>%
    mutate(social_media_usage = I2)
df = df %>%
    mutate(social_media_usage = I3)
df = df %>%
    mutate(social_media_usage = I4)
df = df %>%
    mutate(social_media_usage = I1 + I2)
df = df %>%
    mutate(social_media_usage = I1 + I2 + I3 + I4)
df = df %>%
    mutate(social_media_usage = I1)
df = df %>%
    mutate(social_media_usage = I2)
df = df %>%
    mutate(social_media_usage = I3)
df = df %>%
    mutate(social_media_usage = I4)
df = df %>%
    mutate(social_media_usage = I1 + I2)
df = df %>%
    mutate(social_media_usage = I1 + I2 + I3 + I4)
df = df %>%
    mutate(social_media_usage = I1)
df = df %>%
    mutate(social_media_usage = I2)
df = df %>%
    mutate(social_media_usage = I3)
df = df %>%
    mutate(social_media_usage = I4)
df = df %>%
    mutate(social_media_usage = I1 + I2)
df = df %>%
    mutate(social_media_usage = I1 + I2 + I3 + I4)
df = df %>%
  mutate(
    social_media_usage = branch(
        SM_predictor,
        "I1" ~ I1, "I2" ~ I2, "I3" ~ I3, "I4" ~ I4, # each predictor individually,
        "I1_I2_composite" ~ I1 + I2,
        "I1_I2_I3_I4_composite" ~ I1 + I2 + I3 + I4
  ))

Covariate selection

We consider the inclusion/exclusion of three covariates: , and . However, prior work suggests that including parental_income as a covariate will likely decrease precision, and thus we do not include this variable in our regression.

fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + NULL + physical_activity + factor(has_siblings),
    data = df)
fit = lm(depression ~ social_media_usage + age + NULL + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + NULL + factor(has_siblings), data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + NULL, data = df)
fit = lm(depression ~ social_media_usage + age + physical_activity + factor(has_siblings),
    data = df)
fit = lm(
  depression ~ social_media_usage +
    branch(age_covariate, "not_included" ~ NULL, "included" ~ age) +
    branch(activity_covariate, "not_included" ~ NULL, "included" ~ physical_activity) +
    branch(sibling_covariate, "not_included" ~ NULL, "included" ~ factor(has_siblings)),
  data = df
)

Results

Below, we show the estimated coefficients of our regresion model

model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.93     0.0699     41.9  7.37e-127   2.79       3.06 
2 social_media_usage    0.197    0.0700      2.82 5.20e-  3   0.0593     0.335
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.22     0.131      24.6  1.62e-73   2.96       3.48 
2 social_media_usage       0.185    0.0695      2.66 8.13e- 3   0.0484     0.322
3 factor(has_siblings)1   -0.406    0.154      -2.62 9.11e- 3  -0.710     -0.101
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.62      0.115     40.2   3.24e-122    4.39     4.84  
2 social_media_usage  -0.0327    0.0527    -0.621 5.35e-  1   -0.136    0.0710
3 physical_activity   -0.459     0.0280   -16.4   1.67e- 43   -0.514   -0.404 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.58      0.128     35.7   2.75e-109    4.33    4.83  
2 social_media_usage     -0.0329    0.0527    -0.624 5.33e-  1   -0.137   0.0709
3 physical_activity      -0.464     0.0290   -16.0   5.61e- 42   -0.521  -0.407 
4 factor(has_siblings)1   0.0773    0.117      0.659 5.10e-  1   -0.153   0.308 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic     p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>       <dbl>    <dbl>     <dbl>
1 (Intercept)           4.66     0.927       5.03 0.000000867   2.83     6.48   
2 social_media_usage    0.223    0.0711      3.14 0.00185       0.0835   0.363  
3 age                  -0.127    0.0676     -1.87 0.0619       -0.260    0.00634
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic     p.value conf.…¹ conf.…²
  <chr>                    <dbl>     <dbl>     <dbl>       <dbl>   <dbl>   <dbl>
1 (Intercept)              4.84     0.921       5.26 0.000000283  3.03    6.65  
2 social_media_usage       0.210    0.0707      2.98 0.00316      0.0713  0.349 
3 age                     -0.119    0.0670     -1.78 0.0761      -0.251   0.0126
4 factor(has_siblings)1   -0.394    0.154      -2.56 0.0111      -0.697  -0.0905
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          5.76      0.677      8.51  8.56e-16    4.43     7.09  
2 social_media_usage  -0.0139    0.0537    -0.259 7.96e- 1   -0.119    0.0917
3 age                 -0.0844    0.0491    -1.72  8.69e- 2   -0.181    0.0123
4 physical_activity   -0.456     0.0279   -16.3   3.04e-43   -0.511   -0.401 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             5.73      0.678      8.46  1.29e-15    4.40     7.07  
2 social_media_usage     -0.0139    0.0537    -0.258 7.97e- 1   -0.120    0.0918
3 age                    -0.0855    0.0492    -1.74  8.34e- 2   -0.182    0.0114
4 physical_activity      -0.462     0.0289   -16.0   8.23e-42   -0.518   -0.405 
5 factor(has_siblings)1   0.0835    0.117      0.714 4.76e- 1   -0.147    0.314 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.93     0.0704     41.6  3.97e-126 2.79         3.07 
2 social_media_usage    0.139    0.0705      1.98 4.91e-  2 0.000542     0.278
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.25     0.131      24.7  5.63e-74  2.99        3.51 
2 social_media_usage       0.146    0.0697      2.10 3.65e- 2  0.00928     0.284
3 factor(has_siblings)1   -0.444    0.155      -2.87 4.44e- 3 -0.749      -0.139
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                estimate std.error statistic   p.value conf.low conf.high
  <chr>                  <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)         4.60        0.113    40.8    8.75e-124    4.38      4.82 
2 social_media_usage  0.000872    0.0515    0.0169 9.86e-  1   -0.100     0.102
3 physical_activity  -0.454       0.0273  -16.6    2.82e- 44   -0.508    -0.400
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)            4.56       0.126    36.2    8.70e-111    4.31    4.81  
2 social_media_usage    -0.00194    0.0517   -0.0375 9.70e-  1   -0.104   0.0999
3 physical_activity     -0.459      0.0285  -16.1    1.83e- 42   -0.515  -0.403 
4 factor(has_siblings)1  0.0773     0.118     0.657  5.12e-  1   -0.154   0.309 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)           4.42     0.928       4.76 0.00000308   2.59      6.24  
2 social_media_usage    0.158    0.0712      2.21 0.0275       0.0176    0.298 
3 age                  -0.109    0.0677     -1.61 0.109       -0.242     0.0243
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic     p.value conf.…¹ conf.…²
  <chr>                    <dbl>     <dbl>     <dbl>       <dbl>   <dbl>   <dbl>
1 (Intercept)              4.67     0.922       5.07 0.000000717  2.86    6.48  
2 social_media_usage       0.164    0.0704      2.33 0.0205       0.0255  0.303 
3 age                     -0.104    0.0669     -1.56 0.120       -0.236   0.0273
4 factor(has_siblings)1   -0.439    0.155      -2.84 0.00488     -0.743  -0.134 
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          5.82      0.674      8.63  3.76e-16   4.49     7.14   
2 social_media_usage   0.0165    0.0520     0.316 7.52e- 1  -0.0859   0.119  
3 age                 -0.0895    0.0488    -1.84  6.73e- 2  -0.185    0.00643
4 physical_activity   -0.453     0.0272   -16.6   2.65e-44  -0.507   -0.399  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             5.79      0.676      8.56  6.23e-16   4.46     7.12   
2 social_media_usage      0.0136    0.0522     0.261 7.95e- 1  -0.0891   0.116  
3 age                    -0.0901    0.0488    -1.85  6.58e- 2  -0.186    0.00593
4 physical_activity      -0.458     0.0283   -16.2   1.54e-42  -0.514   -0.403  
5 factor(has_siblings)1   0.0811    0.117      0.692 4.89e- 1  -0.150    0.312  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.93      0.0708    41.4   1.69e-125    2.79     3.07  
2 social_media_usage  -0.0491    0.0709    -0.693 4.89e-  1   -0.189    0.0904
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.24      0.132     24.5   2.65e-73    2.98     3.50  
2 social_media_usage     -0.0594    0.0702    -0.846 3.98e- 1   -0.197    0.0787
3 factor(has_siblings)1  -0.439     0.156     -2.82  5.18e- 3   -0.746   -0.132 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.60      0.111      41.4  2.63e-125    4.38     4.82  
2 social_media_usage  -0.0663    0.0507     -1.31 1.92e-  1   -0.166    0.0335
3 physical_activity   -0.455     0.0269    -16.9  2.20e- 45   -0.508   -0.402 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.57      0.125     36.5   1.41e-111    4.32    4.81  
2 social_media_usage     -0.0648    0.0508    -1.28  2.03e-  1   -0.165   0.0352
3 physical_activity      -0.459     0.0279   -16.4   1.29e- 43   -0.514  -0.404 
4 factor(has_siblings)1   0.0697    0.117      0.595 5.52e-  1   -0.161   0.300 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.08      0.923      4.42  0.0000141    2.26     5.89  
2 social_media_usage  -0.0480    0.0708    -0.678 0.498       -0.187    0.0914
3 age                 -0.0841    0.0673    -1.25  0.212       -0.216    0.0483
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.low conf.…¹
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>    <dbl>   <dbl>
1 (Intercept)             4.31      0.917      4.71  0.00000390    2.51   6.12  
2 social_media_usage     -0.0582    0.0701    -0.830 0.407        -0.196  0.0798
3 age                    -0.0786    0.0666    -1.18  0.239        -0.210  0.0524
4 factor(has_siblings)1  -0.434     0.156     -2.78  0.00575      -0.741 -0.127 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          5.78      0.666       8.68 2.66e-16    4.47    7.09   
2 social_media_usage  -0.0651    0.0505     -1.29 1.98e- 1   -0.165   0.0343 
3 age                 -0.0862    0.0480     -1.80 7.33e- 2   -0.181   0.00818
4 physical_activity   -0.455     0.0268    -17.0  1.34e-45   -0.508  -0.402  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             5.76      0.667      8.63  4.00e-16    4.44    7.07   
2 social_media_usage     -0.0635    0.0506    -1.26  2.10e- 1   -0.163   0.0361 
3 age                    -0.0872    0.0480    -1.82  7.04e- 2   -0.182   0.00732
4 physical_activity      -0.460     0.0278   -16.5   6.93e-44   -0.515  -0.405  
5 factor(has_siblings)1   0.0764    0.117      0.655 5.13e- 1   -0.153   0.306  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.93      0.0707    41.4   1.42e-125    2.79     3.07  
2 social_media_usage  -0.0669    0.0708    -0.945 3.46e-  1   -0.206    0.0725
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.23      0.133     24.4   6.81e-73    2.97     3.49  
2 social_media_usage     -0.0527    0.0703    -0.750 4.54e- 1   -0.191    0.0856
3 factor(has_siblings)1  -0.424     0.156     -2.71  7.08e- 3   -0.731   -0.116 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.61      0.111      41.5  9.31e-126    4.39   4.82    
2 social_media_usage  -0.0986    0.0505     -1.95 5.20e-  2   -0.198  0.000840
3 physical_activity   -0.456     0.0268    -17.0  9.50e- 46   -0.509 -0.403   
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.56      0.125     36.6   7.12e-112    4.31   4.80   
2 social_media_usage     -0.102     0.0508    -2.02  4.47e-  2   -0.202 -0.00242
3 physical_activity      -0.462     0.0279   -16.6   3.57e- 44   -0.517 -0.408  
4 factor(has_siblings)1   0.0975    0.117      0.834 4.05e-  1   -0.133  0.328  
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.02      0.926      4.34  0.0000198    2.19     5.84  
2 social_media_usage  -0.0596    0.0711    -0.839 0.402       -0.199    0.0802
3 age                 -0.0797    0.0675    -1.18  0.239       -0.213    0.0531
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.low conf.…¹
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>    <dbl>   <dbl>
1 (Intercept)             4.26      0.921      4.63  0.00000553    2.45   6.08  
2 social_media_usage     -0.0459    0.0705    -0.652 0.515        -0.185  0.0928
3 age                    -0.0756    0.0668    -1.13  0.259        -0.207  0.0559
4 factor(has_siblings)1  -0.420     0.156     -2.69  0.00762      -0.727 -0.112 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          5.69      0.666       8.54 6.96e-16    4.38    7.00   
2 social_media_usage  -0.0913    0.0506     -1.81 7.20e- 2   -0.191   0.00821
3 age                 -0.0795    0.0480     -1.65 9.91e- 2   -0.174   0.0151 
4 physical_activity   -0.456     0.0267    -17.1  6.83e-46   -0.509  -0.403  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             5.66      0.668      8.47  1.17e-15    4.34    6.97   
2 social_media_usage     -0.0951    0.0508    -1.87  6.21e- 2   -0.195   0.00483
3 age                    -0.0805    0.0481    -1.67  9.52e- 2   -0.175   0.0141 
4 physical_activity      -0.463     0.0278   -16.7   2.32e-44   -0.517  -0.408  
5 factor(has_siblings)1   0.102     0.117      0.876 3.82e- 1   -0.127   0.332  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.93     0.0698     42.0  4.55e-127   2.79       3.06 
2 social_media_usage    0.132    0.0438      3.01 2.80e-  3   0.0458     0.218
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.23     0.130      24.8  2.88e-74   2.98       3.49 
2 social_media_usage       0.130    0.0433      3.00 2.97e- 3   0.0445     0.215
3 factor(has_siblings)1   -0.424    0.154      -2.76 6.17e- 3  -0.726     -0.121
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.61      0.115     40.1   5.73e-122   4.38      4.83  
2 social_media_usage  -0.0125    0.0330    -0.378 7.05e-  1  -0.0775    0.0525
3 physical_activity   -0.457     0.0280   -16.3   3.32e- 43  -0.512    -0.402 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.57      0.128     35.8   1.56e-109   4.32     4.82  
2 social_media_usage     -0.0138    0.0331    -0.416 6.78e-  1  -0.0789   0.0514
3 physical_activity      -0.462     0.0291   -15.9   1.56e- 41  -0.520   -0.405 
4 factor(has_siblings)1   0.0797    0.117      0.678 4.98e-  1  -0.152    0.311 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic     p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>       <dbl>    <dbl>     <dbl>
1 (Intercept)           4.80     0.930       5.16 0.000000460   2.97     6.63   
2 social_media_usage    0.152    0.0447      3.41 0.000751      0.0642   0.240  
3 age                  -0.137    0.0678     -2.01 0.0448       -0.270   -0.00318
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.…¹ conf.h…²
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>   <dbl>    <dbl>
1 (Intercept)              5.01     0.924       5.42    1.22e-7  3.19    6.83   
2 social_media_usage       0.149    0.0442      3.37    8.50e-4  0.0620  0.236  
3 age                     -0.130    0.0671     -1.94    5.30e-2 -0.262   0.00170
4 factor(has_siblings)1   -0.414    0.153      -2.70    7.26e-3 -0.715  -0.113  
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)         5.79       0.680     8.52   8.25e-16   4.46     7.13   
2 social_media_usage  0.00144    0.0338    0.0425 9.66e- 1  -0.0652   0.0680 
3 age                -0.0875     0.0495   -1.77   7.80e- 2  -0.185    0.00986
4 physical_activity  -0.454      0.0279  -16.2    7.23e-43  -0.509   -0.399  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                   estimate std.error statistic  p.value conf.low conf.h…¹
  <chr>                     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>    <dbl>
1 (Intercept)            5.76        0.682    8.45    1.35e-15   4.42    7.11   
2 social_media_usage     0.000214    0.0339   0.00631 9.95e- 1  -0.0665  0.0670 
3 age                   -0.0881      0.0495  -1.78    7.61e- 2  -0.186   0.00931
4 physical_activity     -0.460       0.0290 -15.8     2.85e-41  -0.517  -0.402  
5 factor(has_siblings)1  0.0835      0.117    0.713   4.76e- 1  -0.147   0.314  
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.93      0.0706     41.5  9.11e-126   2.79       3.07 
2 social_media_usage   0.0440    0.0316      1.39 1.65e-  1  -0.0182     0.106
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.24      0.132      24.5  2.02e-73   2.98       3.50 
2 social_media_usage      0.0437    0.0313      1.40 1.63e- 1  -0.0178     0.105
3 factor(has_siblings)1  -0.432     0.155      -2.78 5.83e- 3  -0.738     -0.126
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.64      0.113      41.0  2.48e-124   4.41     4.86   
2 social_media_usage  -0.0407    0.0232     -1.76 7.96e-  2  -0.0863   0.00484
3 physical_activity   -0.465     0.0275    -16.9  2.28e- 45  -0.519   -0.411  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.59      0.126     36.4   2.12e-111   4.35    4.84   
2 social_media_usage     -0.0417    0.0232    -1.80  7.31e-  2  -0.0874  0.00393
3 physical_activity      -0.471     0.0286   -16.5   1.08e- 43  -0.527  -0.414  
4 factor(has_siblings)1   0.0890    0.117      0.762 4.47e-  1  -0.141   0.319  
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)          4.41      0.939       4.69 0.00000408  2.56       6.26  
2 social_media_usage   0.0545    0.0322      1.69 0.0919     -0.00892    0.118 
3 age                 -0.108     0.0685     -1.58 0.114      -0.243      0.0264
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.low conf.…¹
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>    <dbl>   <dbl>
1 (Intercept)             4.64      0.933       4.97 0.00000113  2.80     6.47  
2 social_media_usage      0.0536    0.0319      1.68 0.0933     -0.00906  0.116 
3 age                    -0.103     0.0678     -1.52 0.131      -0.236    0.0306
4 factor(has_siblings)1  -0.425     0.155      -2.74 0.00659    -0.730   -0.119 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          5.62      0.676       8.32 3.31e-15   4.29      6.95  
2 social_media_usage  -0.0334    0.0236     -1.41 1.58e- 1  -0.0799    0.0131
3 age                 -0.0725    0.0490     -1.48 1.40e- 1  -0.169     0.0240
4 physical_activity   -0.463     0.0275    -16.9  3.73e-45  -0.517    -0.409 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             5.59      0.678      8.25  5.44e-15   4.25      6.92  
2 social_media_usage     -0.0344    0.0237    -1.45  1.47e- 1  -0.0810    0.0122
3 age                    -0.0732    0.0491    -1.49  1.37e- 1  -0.170     0.0233
4 physical_activity      -0.469     0.0285   -16.4   1.54e-43  -0.525    -0.413 
5 factor(has_siblings)1   0.0924    0.117      0.792 4.29e- 1  -0.137     0.322 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.97     0.0732     40.5  2.79e-115    2.82      3.11 
2 social_media_usage    0.275    0.0734      3.75 2.18e-  4    0.131     0.420
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.21     0.137      23.4  2.46e-66    2.94     3.48  
2 social_media_usage       0.266    0.0730      3.64 3.30e- 4    0.122    0.409 
3 factor(has_siblings)1   -0.346    0.162      -2.13 3.37e- 2   -0.665   -0.0268
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.68      0.124     37.7   4.10e-108   4.44       4.93 
2 social_media_usage   0.0118    0.0562     0.209 8.34e-  1  -0.0988     0.122
3 physical_activity   -0.471     0.0308   -15.3   2.85e- 38  -0.532     -0.411
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             4.64      0.138     33.5   8.99e-97   4.37       4.91 
2 social_media_usage      0.0113    0.0562     0.200 8.41e- 1  -0.0994     0.122
3 physical_activity      -0.476     0.0317   -15.0   3.05e-37  -0.539     -0.414
4 factor(has_siblings)1   0.0794    0.122      0.649 5.17e- 1  -0.161      0.320
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)           4.83     0.975       4.96 0.00000129    2.91    6.75   
2 social_media_usage    0.302    0.0743      4.06 0.0000645     0.155   0.448  
3 age                  -0.136    0.0711     -1.92 0.0560       -0.276   0.00352
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.…¹ conf.h…²
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>   <dbl>    <dbl>
1 (Intercept)              5.05     0.974       5.19    4.26e-7   3.14   6.97   
2 social_media_usage       0.292    0.0740      3.95    1.01e-4   0.146  0.438  
3 age                     -0.135    0.0706     -1.91    5.76e-2  -0.274  0.00438
4 factor(has_siblings)1   -0.342    0.161      -2.12    3.48e-2  -0.659 -0.0247 
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          6.45      0.714      9.02  4.03e-17   5.04      7.85  
2 social_media_usage   0.0374    0.0565     0.662 5.09e- 1  -0.0739    0.149 
3 age                 -0.129     0.0515    -2.51  1.28e- 2  -0.231    -0.0277
4 physical_activity   -0.471     0.0305   -15.4   1.08e-38  -0.531    -0.411 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             6.41      0.717      8.94  7.40e-17   5.00      7.82  
2 social_media_usage      0.0370    0.0566     0.654 5.14e- 1  -0.0745    0.148 
3 age                    -0.130     0.0516    -2.51  1.26e- 2  -0.231    -0.0280
4 physical_activity      -0.476     0.0314   -15.2   1.11e-37  -0.537    -0.414 
5 factor(has_siblings)1   0.0824    0.121      0.681 4.97e- 1  -0.156     0.321 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.97     0.0741     40.0  4.12e-114   2.82       3.11 
2 social_media_usage    0.204    0.0742      2.75 6.42e-  3   0.0578     0.350
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.25     0.138      23.5  1.45e-66   2.98      3.52  
2 social_media_usage       0.210    0.0736      2.85 4.68e- 3   0.0650    0.355 
3 factor(has_siblings)1   -0.397    0.163      -2.43 1.57e- 2  -0.718    -0.0754
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)         4.69       0.122     38.4   8.77e-110    4.45      4.93 
2 social_media_usage -0.00744    0.0551    -0.135 8.93e-  1   -0.116     0.101
3 physical_activity  -0.474      0.0302   -15.7   1.27e- 39   -0.534    -0.415
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             4.65      0.136     34.2   1.14e-98    4.39     4.92  
2 social_media_usage     -0.0110    0.0554    -0.199 8.42e- 1   -0.120    0.0981
3 physical_activity      -0.480     0.0313   -15.3   2.62e-38   -0.541   -0.418 
4 factor(has_siblings)1   0.0821    0.123      0.668 5.05e- 1   -0.160    0.324 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)           4.66     0.988       4.72 0.00000391   2.71      6.61  
2 social_media_usage    0.229    0.0753      3.03 0.00265      0.0803    0.377 
3 age                  -0.124    0.0720     -1.72 0.0867      -0.266     0.0180
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic     p.value conf.…¹ conf.…²
  <chr>                    <dbl>     <dbl>     <dbl>       <dbl>   <dbl>   <dbl>
1 (Intercept)              4.96     0.987       5.03 0.000000917  3.02    6.91  
2 social_media_usage       0.235    0.0747      3.14 0.00186      0.0878  0.382 
3 age                     -0.125    0.0714     -1.75 0.0811      -0.266   0.0156
4 factor(has_siblings)1   -0.399    0.163      -2.45 0.0149      -0.719  -0.0784
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          6.42      0.716      8.96  6.27e-17   5.01      7.83  
2 social_media_usage   0.0175    0.0556     0.315 7.53e- 1  -0.0919    0.127 
3 age                 -0.126     0.0516    -2.44  1.53e- 2  -0.228    -0.0244
4 physical_activity   -0.475     0.0299   -15.8   3.98e-40  -0.534    -0.416 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             6.38      0.720      8.86  1.28e-16   4.96      7.79  
2 social_media_usage      0.0139    0.0559     0.249 8.03e- 1  -0.0961    0.124 
3 age                    -0.126     0.0516    -2.44  1.55e- 2  -0.227    -0.0241
4 physical_activity      -0.480     0.0310   -15.5   8.74e-39  -0.541    -0.419 
5 factor(has_siblings)1   0.0804    0.122      0.661 5.09e- 1  -0.159     0.320 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.97      0.0750     39.6  5.66e-113   2.82       3.11 
2 social_media_usage   0.0868    0.0751      1.16 2.49e-  1  -0.0611     0.235
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.23      0.141     22.9   1.51e-64   2.95      3.50  
2 social_media_usage      0.0667    0.0752     0.887 3.76e- 1  -0.0813    0.215 
3 factor(has_siblings)1  -0.363     0.167     -2.18  3.02e- 2  -0.691    -0.0349
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.70      0.120     39.1   1.24e-111    4.46     4.93  
2 social_media_usage  -0.0252    0.0539    -0.467 6.41e-  1   -0.131    0.0809
3 physical_activity   -0.475     0.0295   -16.1   5.39e- 41   -0.533   -0.417 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             4.66      0.136     34.3   6.89e-99    4.39     4.92  
2 social_media_usage     -0.0220    0.0542    -0.406 6.85e- 1   -0.129    0.0847
3 physical_activity      -0.479     0.0304   -15.8   6.63e-40   -0.539   -0.420 
4 factor(has_siblings)1   0.0749    0.123      0.610 5.42e- 1   -0.167    0.317 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.28      0.994       4.31 0.0000235   2.32      6.24  
2 social_media_usage   0.101     0.0758      1.33 0.184      -0.0482    0.250 
3 age                 -0.0961    0.0724     -1.33 0.186      -0.239     0.0466
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.low conf.…¹
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>    <dbl>   <dbl>
1 (Intercept)             4.50      0.992       4.53 0.00000878   2.55    6.45  
2 social_media_usage      0.0807    0.0758      1.06 0.288       -0.0686  0.230 
3 age                    -0.0933    0.0720     -1.30 0.196       -0.235   0.0484
4 factor(has_siblings)1  -0.359     0.167      -2.16 0.0318      -0.687  -0.0314
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)         6.37       0.714      8.93  7.67e-17    4.97     7.78  
2 social_media_usage -0.00762    0.0539    -0.141 8.88e- 1   -0.114    0.0986
3 age                -0.122      0.0512    -2.38  1.79e- 2   -0.223   -0.0212
4 physical_activity  -0.477      0.0293   -16.3   1.09e-41   -0.535   -0.420 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)            6.34       0.716     8.86   1.25e-16    4.93     7.75  
2 social_media_usage    -0.00401    0.0542   -0.0740 9.41e- 1   -0.111    0.103 
3 age                   -0.123      0.0513   -2.40   1.72e- 2   -0.224   -0.0220
4 physical_activity     -0.482      0.0301  -16.0    1.24e-40   -0.541   -0.423 
5 factor(has_siblings)1  0.0824     0.122     0.677  4.99e- 1   -0.157    0.322 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.97      0.0750    39.5   7.14e-113   2.82       3.11 
2 social_media_usage   0.0669    0.0752     0.890 3.74e-  1  -0.0811     0.215
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.25      0.140      23.1  2.20e-65   2.97      3.52  
2 social_media_usage      0.0763    0.0747      1.02 3.07e- 1  -0.0707    0.223 
3 factor(has_siblings)1  -0.390     0.166      -2.36 1.91e- 2  -0.717    -0.0643
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.70      0.120     39.2   7.59e-112    4.47     4.94  
2 social_media_usage  -0.0518    0.0539    -0.962 3.37e-  1   -0.158    0.0542
3 physical_activity   -0.477     0.0295   -16.2   2.89e- 41   -0.535   -0.419 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.66      0.134     34.7   7.30e-100    4.39    4.92  
2 social_media_usage     -0.0554    0.0541    -1.02  3.07e-  1   -0.162   0.0512
3 physical_activity      -0.483     0.0305   -15.8   4.85e- 40   -0.543  -0.423 
4 factor(has_siblings)1   0.0909    0.122      0.742 4.59e-  1   -0.150   0.332 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.15      0.987      4.20  0.0000361   2.21      6.09  
2 social_media_usage   0.0724    0.0753     0.961 0.337      -0.0758    0.221 
3 age                 -0.0865    0.0720    -1.20  0.230      -0.228     0.0552
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.44      0.986       4.50 0.0000103   2.50     6.38  
2 social_media_usage      0.0818    0.0747      1.10 0.274      -0.0653   0.229 
3 age                    -0.0870    0.0713     -1.22 0.224      -0.228    0.0534
4 factor(has_siblings)1  -0.391     0.165      -2.36 0.0188     -0.717   -0.0652
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          6.36      0.708      8.99  5.20e-17    4.97     7.76  
2 social_media_usage  -0.0450    0.0535    -0.841 4.01e- 1   -0.150    0.0603
3 age                 -0.121     0.0507    -2.38  1.81e- 2   -0.221   -0.0208
4 physical_activity   -0.480     0.0293   -16.4   5.05e-42   -0.538   -0.422 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             6.32      0.711      8.89  1.00e-16    4.92     7.72  
2 social_media_usage     -0.0486    0.0537    -0.905 3.66e- 1   -0.154    0.0572
3 age                    -0.121     0.0508    -2.38  1.79e- 2   -0.221   -0.0210
4 physical_activity      -0.486     0.0303   -16.0   8.50e-41   -0.546   -0.426 
5 factor(has_siblings)1   0.0931    0.121      0.767 4.44e- 1   -0.146    0.332 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.97     0.0732     40.5  2.25e-115   2.82       3.11 
2 social_media_usage    0.164    0.0428      3.82 1.67e-  4   0.0793     0.248
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.23     0.137      23.7  4.63e-67   2.96      3.50  
2 social_media_usage       0.162    0.0425      3.81 1.71e- 4   0.0784    0.246 
3 factor(has_siblings)1   -0.372    0.161      -2.30 2.20e- 2  -0.689    -0.0539
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)         4.69       0.125    37.6    8.49e-108   4.44      4.93  
2 social_media_usage  0.00139    0.0330    0.0422 9.66e-  1  -0.0636    0.0664
3 physical_activity  -0.473      0.0310  -15.3    3.74e- 38  -0.534    -0.412 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                    estimate std.error  statistic  p.value conf.…¹ conf.…²
  <chr>                      <dbl>     <dbl>      <dbl>    <dbl>   <dbl>   <dbl>
1 (Intercept)            4.65         0.138   33.6      4.26e-97  4.38    4.92  
2 social_media_usage    -0.0000325    0.0331  -0.000982 9.99e- 1 -0.0652  0.0651
3 physical_activity     -0.478        0.0320 -15.0      5.77e-37 -0.541  -0.415 
4 factor(has_siblings)1  0.0797       0.123    0.651    5.16e- 1 -0.162   0.321 
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic     p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>       <dbl>    <dbl>     <dbl>
1 (Intercept)           5.00     0.980       5.10 0.000000642   3.07     6.93   
2 social_media_usage    0.184    0.0436      4.21 0.0000355     0.0977   0.270  
3 age                  -0.149    0.0714     -2.08 0.0384       -0.289   -0.00798
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.…¹ conf.h…²
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>   <dbl>    <dbl>
1 (Intercept)              5.26     0.978       5.37    1.70e-7  3.33    7.18   
2 social_media_usage       0.182    0.0433      4.20    3.61e-5  0.0967  0.267  
3 age                     -0.148    0.0708     -2.09    3.77e-2 -0.287  -0.00849
4 factor(has_siblings)1   -0.370    0.160      -2.31    2.17e-2 -0.686  -0.0547 
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          6.45      0.718      8.99  5.23e-17   5.04      7.87  
2 social_media_usage   0.0195    0.0335     0.582 5.61e- 1  -0.0464    0.0853
3 age                 -0.130     0.0519    -2.50  1.32e- 2  -0.232    -0.0273
4 physical_activity   -0.471     0.0307   -15.4   2.01e-38  -0.532    -0.411 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             6.41      0.721      8.89  1.03e-16   4.99      7.83  
2 social_media_usage      0.0180    0.0336     0.537 5.92e- 1  -0.0481    0.0841
3 age                    -0.129     0.0520    -2.49  1.34e- 2  -0.232    -0.0271
4 physical_activity      -0.476     0.0317   -15.0   3.15e-37  -0.539    -0.414 
5 factor(has_siblings)1   0.0791    0.121      0.652 5.15e- 1  -0.160     0.318 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.97      0.0736     40.3  1.01e-114   2.82       3.11 
2 social_media_usage   0.0942    0.0285      3.31 1.07e-  3   0.0381     0.150
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.23      0.138      23.4  2.69e-66   2.95      3.50  
2 social_media_usage      0.0918    0.0283      3.25 1.31e- 3   0.0362    0.147 
3 factor(has_siblings)1  -0.362     0.163      -2.22 2.69e- 2  -0.682    -0.0416
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.71      0.124     37.9   1.79e-108   4.46      4.95  
2 social_media_usage  -0.0119    0.0217    -0.547 5.85e-  1  -0.0546    0.0309
3 physical_activity   -0.479     0.0309   -15.5   5.67e- 39  -0.540    -0.418 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             4.67      0.138     33.8   1.98e-97   4.40      4.94  
2 social_media_usage     -0.0125    0.0218    -0.574 5.66e- 1  -0.0553    0.0303
3 physical_activity      -0.484     0.0318   -15.2   7.27e-38  -0.547    -0.421 
4 factor(has_siblings)1   0.0826    0.122      0.675 5.00e- 1  -0.158     0.323 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)           4.90     0.988       4.96 0.00000124   2.96    6.85    
2 social_media_usage    0.107    0.0290      3.68 0.000282     0.0497  0.164   
3 age                  -0.142    0.0720     -1.97 0.0503      -0.283   0.000196
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.…¹ conf.h…²
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>   <dbl>    <dbl>
1 (Intercept)              5.14     0.986       5.21    3.77e-7  3.20    7.08e+0
2 social_media_usage       0.104    0.0288      3.62    3.52e-4  0.0477  1.61e-1
3 age                     -0.140    0.0715     -1.96    5.09e-2 -0.281   5.53e-4
4 factor(has_siblings)1   -0.359    0.162      -2.22    2.73e-2 -0.677  -4.05e-2
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                estimate std.error statistic  p.value conf.low conf.high
  <chr>                  <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)         6.38        0.719     8.87   1.13e-16   4.97      7.80  
2 social_media_usage -0.000458    0.0221   -0.0207 9.83e- 1  -0.0439    0.0430
3 age                -0.123       0.0520   -2.36   1.89e- 2  -0.225    -0.0204
4 physical_activity  -0.477       0.0306  -15.6    3.36e-39  -0.537    -0.417 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)            6.34       0.722     8.78   2.15e-16   4.92      7.76  
2 social_media_usage    -0.00106    0.0221   -0.0478 9.62e- 1  -0.0446    0.0425
3 age                   -0.123      0.0520   -2.36   1.89e- 2  -0.225    -0.0204
4 physical_activity     -0.482      0.0316  -15.3    4.22e-38  -0.544    -0.420 
5 factor(has_siblings)1  0.0835     0.121     0.689  4.91e- 1  -0.155     0.322 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.96     0.0720     41.1  1.54e-119    2.82      3.10 
2 social_media_usage    0.251    0.0722      3.48 5.85e-  4    0.109     0.393
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.22     0.135      23.8  8.94e-69   2.95      3.48  
2 social_media_usage       0.240    0.0718      3.35 9.31e- 4   0.0989    0.381 
3 factor(has_siblings)1   -0.363    0.159      -2.28 2.34e- 2  -0.677    -0.0495
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.68      0.123     38.2   7.33e-112    4.44     4.93  
2 social_media_usage  -0.0171    0.0554    -0.308 7.58e-  1   -0.126    0.0920
3 physical_activity   -0.476     0.0305   -15.6   1.20e- 39   -0.536   -0.416 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.64      0.137     34.0   2.33e-100    4.38    4.91  
2 social_media_usage     -0.0175    0.0555    -0.316 7.52e-  1   -0.127   0.0917
3 physical_activity      -0.481     0.0315   -15.3   1.72e- 38   -0.543  -0.419 
4 factor(has_siblings)1   0.0819    0.121      0.677 4.99e-  1   -0.156   0.320 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)           4.50     0.948       4.74 0.00000342    2.63     6.36  
2 social_media_usage    0.273    0.0732      3.73 0.000234      0.129    0.417 
3 age                  -0.113    0.0693     -1.63 0.105        -0.249    0.0236
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.low conf.…¹
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>    <dbl>   <dbl>
1 (Intercept)              4.72     0.946       4.98 0.00000111    2.85   6.58  
2 social_media_usage       0.262    0.0728      3.59 0.000386      0.118  0.405 
3 age                     -0.110    0.0688     -1.60 0.111        -0.245  0.0255
4 factor(has_siblings)1   -0.359    0.159      -2.26 0.0249       -0.672 -0.0456
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)         6.16       0.698     8.83   1.29e-16    4.79    7.54   
2 social_media_usage  0.00418    0.0559    0.0747 9.41e- 1   -0.106   0.114  
3 age                -0.108      0.0504   -2.15   3.23e- 2   -0.208  -0.00921
4 physical_activity  -0.475      0.0303  -15.7    6.15e-40   -0.535  -0.416  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)            6.13       0.700     8.75   2.22e-16    4.75    7.51   
2 social_media_usage     0.00381    0.0560    0.0681 9.46e- 1   -0.106   0.114  
3 age                   -0.109      0.0505   -2.16   3.15e- 2   -0.208  -0.00974
4 physical_activity     -0.481      0.0313  -15.4    8.14e-39   -0.542  -0.419  
5 factor(has_siblings)1  0.0865     0.120     0.719  4.72e- 1   -0.150   0.323  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.96     0.0723     40.9  4.09e-119   2.81       3.10 
2 social_media_usage    0.226    0.0725      3.12 2.00e-  3   0.0834     0.369
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.26     0.135      24.1  1.08e-69   2.99       3.52 
2 social_media_usage       0.232    0.0717      3.23 1.37e- 3   0.0908     0.373
3 factor(has_siblings)1   -0.415    0.159      -2.60 9.73e- 3  -0.729     -0.101
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                estimate std.error statistic   p.value conf.low conf.high
  <chr>                  <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)         4.67        0.121    38.5    7.84e-113    4.44      4.91 
2 social_media_usage  0.000624    0.0546    0.0114 9.91e-  1   -0.107     0.108
3 physical_activity  -0.473       0.0301  -15.7    4.02e- 40   -0.532    -0.413
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)            4.64       0.134    34.5    8.47e-102    4.37     4.90 
2 social_media_usage    -0.00324    0.0550   -0.0590 9.53e-  1   -0.111    0.105
3 physical_activity     -0.478      0.0313  -15.3    1.26e- 38   -0.540   -0.417
4 factor(has_siblings)1  0.0822     0.122     0.675  5.00e-  1   -0.157    0.322
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)           4.48     0.955       4.69 0.00000428    2.60     6.36  
2 social_media_usage    0.249    0.0737      3.38 0.000825      0.104    0.394 
3 age                  -0.112    0.0697     -1.60 0.111        -0.249    0.0258
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic     p.value conf.…¹ conf.…²
  <chr>                    <dbl>     <dbl>     <dbl>       <dbl>   <dbl>   <dbl>
1 (Intercept)              4.78     0.952       5.02 0.000000928   2.91   6.65  
2 social_media_usage       0.255    0.0729      3.50 0.000548      0.112  0.399 
3 age                     -0.112    0.0690     -1.62 0.107        -0.247  0.0243
4 factor(has_siblings)1   -0.415    0.159      -2.61 0.00951      -0.728 -0.102 
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          6.20      0.700      8.86  1.04e-16   4.82      7.58  
2 social_media_usage   0.0238    0.0552     0.431 6.67e- 1  -0.0849    0.133 
3 age                 -0.112     0.0505    -2.22  2.76e- 2  -0.211    -0.0125
4 physical_activity   -0.473     0.0299   -15.8   1.73e-40  -0.531    -0.414 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             6.16      0.703      8.77  2.02e-16   4.78      7.55  
2 social_media_usage      0.0199    0.0556     0.358 7.20e- 1  -0.0895    0.129 
3 age                    -0.112     0.0506    -2.21  2.77e- 2  -0.211    -0.0123
4 physical_activity      -0.478     0.0310   -15.4   5.51e-39  -0.539    -0.417 
5 factor(has_siblings)1   0.0821    0.121      0.680 4.97e- 1  -0.156     0.320 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.96      0.0735    40.2   2.01e-117   2.81       3.10 
2 social_media_usage   0.0504    0.0737     0.684 4.94e-  1  -0.0946     0.195
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.24      0.138     23.5   1.42e-67    2.97     3.51  
2 social_media_usage      0.0338    0.0734     0.460 6.46e- 1   -0.111    0.178 
3 factor(has_siblings)1  -0.392     0.163     -2.40  1.70e- 2   -0.712   -0.0707
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.68      0.118     39.6   1.36e-115    4.45     4.91  
2 social_media_usage  -0.0366    0.0529    -0.691 4.90e-  1   -0.141    0.0676
3 physical_activity   -0.475     0.0292   -16.3   3.34e- 42   -0.532   -0.417 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.64      0.133     34.9   8.03e-103    4.38    4.91  
2 social_media_usage     -0.0342    0.0531    -0.644 5.20e-  1   -0.139   0.0704
3 physical_activity      -0.479     0.0301   -15.9   6.71e- 41   -0.539  -0.420 
4 factor(has_siblings)1   0.0758    0.121      0.625 5.32e-  1   -0.163   0.315 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          3.95      0.963      4.10  0.0000534   2.06      5.85  
2 social_media_usage   0.0607    0.0743     0.817 0.414      -0.0856    0.207 
3 age                 -0.0730    0.0703    -1.04  0.300      -0.212     0.0655
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.19      0.960      4.36  0.0000181    2.30    6.08  
2 social_media_usage      0.0438    0.0740     0.592 0.555       -0.102   0.190 
3 age                    -0.0699    0.0698    -1.00  0.317       -0.207   0.0675
4 factor(has_siblings)1  -0.388     0.163     -2.38  0.0179      -0.709  -0.0675
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          6.12      0.697      8.79  1.71e-16    4.75    7.50   
2 social_media_usage  -0.0221    0.0530    -0.417 6.77e- 1   -0.127   0.0823 
3 age                 -0.105     0.0500    -2.10  3.66e- 2   -0.204  -0.00659
4 physical_activity   -0.477     0.0290   -16.5   8.94e-43   -0.534  -0.420  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             6.10      0.699      8.72  2.68e-16    4.72    7.47   
2 social_media_usage     -0.0194    0.0532    -0.363 7.17e- 1   -0.124   0.0855 
3 age                    -0.106     0.0501    -2.12  3.51e- 2   -0.205  -0.00746
4 physical_activity      -0.482     0.0299   -16.1   1.65e-41   -0.541  -0.423  
5 factor(has_siblings)1   0.0833    0.121      0.691 4.90e- 1   -0.154   0.321  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.96      0.0735    40.2   1.85e-117   2.81       3.10 
2 social_media_usage   0.0601    0.0736     0.816 4.15e-  1  -0.0849     0.205
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.26      0.138      23.6  4.12e-68   2.99      3.53  
2 social_media_usage      0.0795    0.0733      1.08 2.79e- 1  -0.0648    0.224 
3 factor(has_siblings)1  -0.417     0.163      -2.56 1.10e- 2  -0.737    -0.0963
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.68      0.118     39.6   1.63e-115    4.45     4.92  
2 social_media_usage  -0.0385    0.0530    -0.726 4.68e-  1   -0.143    0.0658
3 physical_activity   -0.475     0.0292   -16.3   3.60e- 42   -0.533   -0.418 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.64      0.132     35.1   2.57e-103    4.38    4.90  
2 social_media_usage     -0.0442    0.0535    -0.826 4.09e-  1   -0.150   0.0612
3 physical_activity      -0.481     0.0303   -15.9   9.48e- 41   -0.541  -0.422 
4 factor(has_siblings)1   0.0953    0.122      0.781 4.36e-  1   -0.145   0.335 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          3.86      0.955      4.05  0.0000676   1.98      5.74  
2 social_media_usage   0.0613    0.0737     0.833 0.406      -0.0837    0.206 
3 age                 -0.0664    0.0697    -0.952 0.342      -0.204     0.0709
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.15      0.952      4.36  0.0000183   2.28     6.03  
2 social_media_usage      0.0807    0.0733     1.10  0.272      -0.0636   0.225 
3 age                    -0.0656    0.0690    -0.951 0.343      -0.202    0.0703
4 factor(has_siblings)1  -0.416     0.163     -2.56  0.0111     -0.737   -0.0956
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          6.16      0.692      8.90  7.81e-17    4.80    7.52   
2 social_media_usage  -0.0371    0.0526    -0.704 4.82e- 1   -0.141   0.0666 
3 age                 -0.107     0.0496    -2.17  3.12e- 2   -0.205  -0.00975
4 physical_activity   -0.478     0.0290   -16.5   7.70e-43   -0.535  -0.421  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             6.12      0.694      8.82  1.38e-16    4.76     7.49  
2 social_media_usage     -0.0431    0.0532    -0.810 4.18e- 1   -0.148    0.0616
3 age                    -0.108     0.0496    -2.18  3.02e- 2   -0.206   -0.0104
4 physical_activity      -0.485     0.0301   -16.1   1.95e-41   -0.544   -0.426 
5 factor(has_siblings)1   0.100     0.121      0.825 4.10e- 1   -0.139    0.339 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.96     0.0716     41.3  4.24e-120   2.82       3.10 
2 social_media_usage    0.165    0.0421      3.90 1.19e-  4   0.0816     0.248
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.23     0.134      24.1  7.45e-70   2.97      3.50  
2 social_media_usage       0.163    0.0418      3.89 1.26e- 4   0.0803    0.245 
3 factor(has_siblings)1   -0.386    0.158      -2.44 1.52e- 2  -0.697    -0.0751
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)         4.68       0.124     37.8   5.49e-111   4.44      4.92  
2 social_media_usage -0.00578    0.0329    -0.176 8.61e-  1  -0.0705    0.0589
3 physical_activity  -0.475      0.0308   -15.4   5.53e- 39  -0.535    -0.414 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)            4.64       0.137     34.0   2.65e-100   4.37     4.91  
2 social_media_usage    -0.00737    0.0330    -0.223 8.23e-  1  -0.0723   0.0576
3 physical_activity     -0.480      0.0319   -15.0   1.15e- 37  -0.543   -0.417 
4 factor(has_siblings)1  0.0833     0.121      0.687 4.93e-  1  -0.155    0.322 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)           4.74     0.950       5.00 0.00000104   2.88     6.61   
2 social_media_usage    0.183    0.0430      4.24 0.0000299    0.0980   0.267  
3 age                  -0.131    0.0694     -1.89 0.0600      -0.268    0.00556
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.…¹ conf.h…²
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>   <dbl>    <dbl>
1 (Intercept)              5.00     0.947       5.28    2.68e-7  3.13    6.86   
2 social_media_usage       0.180    0.0427      4.23    3.21e-5  0.0964  0.264  
3 age                     -0.129    0.0688     -1.88    6.13e-2 -0.265   0.00616
4 factor(has_siblings)1   -0.383    0.157      -2.43    1.55e-2 -0.693  -0.0733 
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          6.19      0.702      8.82  1.36e-16   4.81      7.57  
2 social_media_usage   0.0102    0.0335     0.305 7.60e- 1  -0.0556    0.0761
3 age                 -0.111     0.0508    -2.19  2.96e- 2  -0.211    -0.0111
4 physical_activity   -0.473     0.0306   -15.4   4.12e-39  -0.533    -0.413 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)            6.15       0.705      8.73  2.53e-16   4.77      7.54  
2 social_media_usage     0.00863    0.0336     0.257 7.97e- 1  -0.0574    0.0747
3 age                   -0.111      0.0509    -2.19  2.95e- 2  -0.212    -0.0111
4 physical_activity     -0.479      0.0317   -15.1   8.29e-38  -0.541    -0.416 
5 factor(has_siblings)1  0.0845     0.120      0.701 4.84e- 1  -0.153     0.322 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.96      0.0722     40.9  2.91e-119   2.81       3.10 
2 social_media_usage   0.0940    0.0289      3.25 1.30e-  3   0.0370     0.151
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.24      0.135      24.0  2.37e-69   2.97      3.51  
2 social_media_usage      0.0933    0.0287      3.25 1.28e- 3   0.0369    0.150 
3 factor(has_siblings)1  -0.393     0.159      -2.47 1.41e- 2  -0.707    -0.0798
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.70      0.123     38.2   4.18e-112   4.46      4.94  
2 social_media_usage  -0.0158    0.0222    -0.713 4.76e-  1  -0.0595    0.0279
3 physical_activity   -0.480     0.0306   -15.7   4.63e- 40  -0.540    -0.419 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.66      0.136     34.3   3.21e-101   4.39     4.92  
2 social_media_usage     -0.0170    0.0223    -0.765 4.45e-  1  -0.0609   0.0268
3 physical_activity      -0.486     0.0317   -15.3   9.99e- 39  -0.548   -0.423 
4 factor(has_siblings)1   0.0884    0.121      0.729 4.67e-  1  -0.150    0.327 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)           4.57     0.956       4.78 0.00000290   2.69      6.45  
2 social_media_usage    0.105    0.0295      3.54 0.000462     0.0465    0.163 
3 age                  -0.118    0.0699     -1.69 0.0922      -0.256     0.0195
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic     p.value conf.…¹ conf.…²
  <chr>                    <dbl>     <dbl>     <dbl>       <dbl>   <dbl>   <dbl>
1 (Intercept)              4.83     0.954       5.07 0.000000750  2.95    6.71  
2 social_media_usage       0.104    0.0293      3.55 0.000456     0.0462  0.161 
3 age                     -0.117    0.0692     -1.68 0.0932      -0.253   0.0197
4 factor(has_siblings)1   -0.391    0.159      -2.46 0.0144      -0.704  -0.0786
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)         6.13       0.701      8.74  2.40e-16   4.75     7.51   
2 social_media_usage -0.00615    0.0226    -0.273 7.85e- 1  -0.0506   0.0383 
3 age                -0.105      0.0507    -2.07  3.95e- 2  -0.205   -0.00507
4 physical_activity  -0.479      0.0304   -15.7   3.13e-40  -0.538   -0.419  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)            6.09       0.704      8.65  4.53e-16   4.70     7.47   
2 social_media_usage    -0.00736    0.0226    -0.325 7.45e- 1  -0.0519   0.0372 
3 age                   -0.105      0.0508    -2.07  3.94e- 2  -0.205   -0.00515
4 physical_activity     -0.485      0.0315   -15.4   6.63e-39  -0.547   -0.423  
5 factor(has_siblings)1  0.0894     0.121      0.742 4.59e- 1  -0.148    0.327  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.96     0.0718     41.2  3.30e-120    2.82      3.10 
2 social_media_usage    0.254    0.0719      3.53 4.83e-  4    0.112     0.396
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.22     0.135      23.8  5.79e-69    2.95     3.48  
2 social_media_usage       0.244    0.0716      3.41 7.51e- 4    0.103    0.385 
3 factor(has_siblings)1   -0.358    0.159      -2.25 2.51e- 2   -0.672   -0.0451
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.67      0.122     38.4   1.08e-112    4.43     4.91  
2 social_media_usage  -0.0183    0.0554    -0.331 7.41e-  1   -0.127    0.0907
3 physical_activity   -0.473     0.0303   -15.6   9.46e- 40   -0.533   -0.414 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.64      0.136     34.1   9.26e-101    4.37    4.90  
2 social_media_usage     -0.0188    0.0554    -0.340 7.34e-  1   -0.128   0.0903
3 physical_activity      -0.478     0.0313   -15.3   1.32e- 38   -0.539  -0.416 
4 factor(has_siblings)1   0.0753    0.121      0.624 5.33e-  1   -0.162   0.313 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)           4.50     0.947       4.74 0.00000335    2.63     6.36  
2 social_media_usage    0.276    0.0730      3.78 0.000191      0.132    0.420 
3 age                  -0.112    0.0692     -1.62 0.105        -0.249    0.0238
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.low conf.…¹
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>    <dbl>   <dbl>
1 (Intercept)              4.71     0.946       4.98 0.00000112    2.85   6.57  
2 social_media_usage       0.265    0.0726      3.65 0.000309      0.122  0.408 
3 age                     -0.110    0.0687     -1.59 0.112        -0.245  0.0257
4 factor(has_siblings)1   -0.354    0.159      -2.23 0.0267       -0.666 -0.0412
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)         6.16       0.698     8.83   1.29e-16    4.78    7.53   
2 social_media_usage  0.00301    0.0559    0.0539 9.57e- 1   -0.107   0.113  
3 age                -0.109      0.0504   -2.16   3.17e- 2   -0.208  -0.00960
4 physical_activity  -0.473      0.0301  -15.7    4.75e-40   -0.532  -0.414  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)            6.13       0.700     8.75   2.20e-16    4.75     7.50  
2 social_media_usage     0.00260    0.0560    0.0465 9.63e- 1   -0.108    0.113 
3 age                   -0.109      0.0504   -2.17   3.10e- 2   -0.209   -0.0101
4 physical_activity     -0.478      0.0311  -15.4    6.13e-39   -0.539   -0.417 
5 factor(has_siblings)1  0.0800     0.120     0.668  5.05e- 1   -0.156    0.316 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.96     0.0721     41.1  7.92e-120   2.82       3.10 
2 social_media_usage    0.232    0.0722      3.22 1.44e-  3   0.0903     0.375
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.26     0.135      24.1  5.88e-70   2.99      3.52  
2 social_media_usage       0.239    0.0715      3.35 9.36e- 4   0.0985    0.380 
3 factor(has_siblings)1   -0.413    0.159      -2.59 1.00e- 2  -0.726    -0.0994
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)         4.66       0.121    38.7    1.54e-113    4.43      4.90 
2 social_media_usage -0.00443    0.0547   -0.0809 9.36e-  1   -0.112     0.103
3 physical_activity  -0.471      0.0300  -15.7    3.60e- 40   -0.530    -0.412
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)            4.63       0.134     34.6   3.53e-102    4.36     4.89 
2 social_media_usage    -0.00831    0.0551    -0.151 8.80e-  1   -0.117    0.100
3 physical_activity     -0.476      0.0311   -15.3   1.13e- 38   -0.537   -0.415
4 factor(has_siblings)1  0.0768     0.121      0.632 5.28e-  1   -0.162    0.316
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)           4.49     0.953       4.71 0.00000399    2.61     6.36  
2 social_media_usage    0.256    0.0734      3.48 0.000582      0.111    0.400 
3 age                  -0.112    0.0696     -1.61 0.110        -0.249    0.0253
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic     p.value conf.…¹ conf.…²
  <chr>                    <dbl>     <dbl>     <dbl>       <dbl>   <dbl>   <dbl>
1 (Intercept)              4.79     0.950       5.03 0.000000866   2.91   6.66  
2 social_media_usage       0.263    0.0727      3.61 0.000365      0.119  0.406 
3 age                     -0.112    0.0689     -1.62 0.106        -0.248  0.0238
4 factor(has_siblings)1   -0.413    0.159      -2.60 0.00978      -0.725 -0.100 
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          6.19      0.699      8.85  1.12e-16   4.81      7.56  
2 social_media_usage   0.0187    0.0553     0.339 7.35e- 1  -0.0901    0.128 
3 age                 -0.112     0.0505    -2.21  2.80e- 2  -0.211    -0.0121
4 physical_activity   -0.471     0.0298   -15.8   1.58e-40  -0.529    -0.412 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             6.15      0.703      8.75  2.15e-16   4.77      7.53  
2 social_media_usage      0.0149    0.0557     0.267 7.90e- 1  -0.0948    0.125 
3 age                    -0.111     0.0505    -2.21  2.82e- 2  -0.211    -0.0120
4 physical_activity      -0.476     0.0309   -15.4   5.07e-39  -0.537    -0.415 
5 factor(has_siblings)1   0.0766    0.121      0.635 5.26e- 1  -0.161     0.314 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.96      0.0734    40.4   4.98e-118   2.82       3.10 
2 social_media_usage   0.0524    0.0735     0.713 4.76e-  1  -0.0922     0.197
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.24      0.138     23.5   1.09e-67    2.97     3.51  
2 social_media_usage      0.0363    0.0732     0.496 6.20e- 1   -0.108    0.180 
3 factor(has_siblings)1  -0.385     0.163     -2.37  1.86e- 2   -0.706   -0.0648
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.67      0.117     39.9   1.55e-116    4.44     4.90  
2 social_media_usage  -0.0374    0.0528    -0.709 4.79e-  1   -0.141    0.0665
3 physical_activity   -0.472     0.0289   -16.3   2.24e- 42   -0.529   -0.415 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.63      0.133     35.0   3.02e-103    4.37    4.90  
2 social_media_usage     -0.0353    0.0530    -0.666 5.06e-  1   -0.140   0.0690
3 physical_activity      -0.476     0.0298   -16.0   4.28e- 41   -0.535  -0.418 
4 factor(has_siblings)1   0.0691    0.121      0.572 5.68e-  1   -0.169   0.307 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          3.95      0.963      4.10  0.0000548   2.05      5.84  
2 social_media_usage   0.0627    0.0742     0.845 0.399      -0.0833    0.209 
3 age                 -0.0721    0.0703    -1.03  0.306      -0.211     0.0663
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.18      0.960      4.35  0.0000191   2.29     6.07  
2 social_media_usage      0.0463    0.0739     0.626 0.532      -0.0992   0.192 
3 age                    -0.0689    0.0697    -0.988 0.324      -0.206    0.0684
4 factor(has_siblings)1  -0.382     0.163     -2.35  0.0196     -0.703   -0.0616
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          6.12      0.696      8.79  1.69e-16    4.75    7.49   
2 social_media_usage  -0.0229    0.0529    -0.433 6.66e- 1   -0.127   0.0813 
3 age                 -0.105     0.0500    -2.11  3.58e- 2   -0.204  -0.00707
4 physical_activity   -0.475     0.0288   -16.5   5.80e-43   -0.531  -0.418  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             6.09      0.698      8.73  2.63e-16    4.72    7.47   
2 social_media_usage     -0.0204    0.0531    -0.384 7.01e- 1   -0.125   0.0842 
3 age                    -0.106     0.0501    -2.13  3.44e- 2   -0.205  -0.00787
4 physical_activity      -0.479     0.0297   -16.2   1.02e-41   -0.538  -0.421  
5 factor(has_siblings)1   0.0767    0.120      0.639 5.24e- 1   -0.160   0.313  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.96      0.0733     40.4  3.81e-118   2.82       3.10 
2 social_media_usage   0.0782    0.0734      1.07 2.87e-  1  -0.0663     0.223
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.26      0.138      23.7  2.22e-68   2.99      3.53  
2 social_media_usage      0.0988    0.0731      1.35 1.78e- 1  -0.0451    0.243 
3 factor(has_siblings)1  -0.417     0.163      -2.56 1.09e- 2  -0.737    -0.0969
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.68      0.118     39.8   2.68e-116    4.45     4.91  
2 social_media_usage  -0.0502    0.0531    -0.946 3.45e-  1   -0.155    0.0543
3 physical_activity   -0.474     0.0291   -16.3   2.52e- 42   -0.531   -0.417 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.63      0.132     35.2   7.98e-104    4.37    4.89  
2 social_media_usage     -0.0565    0.0537    -1.05  2.94e-  1   -0.162   0.0493
3 physical_activity      -0.480     0.0302   -15.9   6.75e- 41   -0.540  -0.421 
4 factor(has_siblings)1   0.0942    0.122      0.773 4.40e-  1   -0.146   0.334 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          3.86      0.953      4.05  0.0000667   1.98      5.74  
2 social_media_usage   0.0799    0.0734     1.09  0.277      -0.0647    0.224 
3 age                 -0.0659    0.0696    -0.947 0.345      -0.203     0.0711
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.15      0.951      4.37  0.0000179   2.28     6.02  
2 social_media_usage      0.100     0.0731     1.37  0.171      -0.0435   0.244 
3 age                    -0.0652    0.0689    -0.946 0.345      -0.201    0.0705
4 factor(has_siblings)1  -0.416     0.163     -2.56  0.0110     -0.737   -0.0962
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)          6.16      0.691      8.91  7.24e-17    4.80     7.52  
2 social_media_usage  -0.0483    0.0527    -0.917 3.60e- 1   -0.152    0.0555
3 age                 -0.108     0.0495    -2.17  3.07e- 2   -0.205   -0.0101
4 physical_activity   -0.477     0.0289   -16.5   5.28e-43   -0.534   -0.420 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             6.12      0.693      8.83  1.28e-16    4.75     7.48  
2 social_media_usage     -0.0549    0.0534    -1.03  3.04e- 1   -0.160    0.0501
3 age                    -0.108     0.0495    -2.19  2.97e- 2   -0.206   -0.0107
4 physical_activity      -0.484     0.0300   -16.1   1.36e-41   -0.543   -0.425 
5 factor(has_siblings)1   0.0990    0.121      0.818 4.14e- 1   -0.139    0.337 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)           2.96     0.0714     41.5  8.06e-121   2.82       3.10 
2 social_media_usage    0.167    0.0420      3.99 8.46e-  5   0.0848     0.250
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)              3.24     0.134      24.2  4.03e-70   2.97      3.50  
2 social_media_usage       0.166    0.0416      3.99 8.56e- 5   0.0840    0.248 
3 factor(has_siblings)1   -0.383    0.158      -2.43 1.58e- 2  -0.694    -0.0727
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)         4.67       0.123     38.0   1.10e-111   4.43      4.91  
2 social_media_usage -0.00806    0.0329    -0.245 8.06e-  1  -0.0728    0.0566
3 physical_activity  -0.473      0.0307   -15.4   5.00e- 39  -0.533    -0.412 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)            4.63       0.136     34.1   1.12e-100   4.37     4.90  
2 social_media_usage    -0.00965    0.0330    -0.293 7.70e-  1  -0.0746   0.0553
3 physical_activity     -0.478      0.0318   -15.0   1.03e- 37  -0.540   -0.415 
4 factor(has_siblings)1  0.0774     0.121      0.640 5.23e-  1  -0.161    0.316 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic     p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>       <dbl>    <dbl>     <dbl>
1 (Intercept)           4.75     0.948       5.01 0.000000964    2.89    6.62   
2 social_media_usage    0.186    0.0428      4.33 0.0000208      0.101   0.270  
3 age                  -0.131    0.0693     -1.89 0.0592        -0.268   0.00512
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic    p.value conf.…¹ conf.h…²
  <chr>                    <dbl>     <dbl>     <dbl>      <dbl>   <dbl>    <dbl>
1 (Intercept)              5.00     0.946       5.29    2.50e-7   3.14   6.86   
2 social_media_usage       0.184    0.0425      4.33    2.12e-5   0.100  0.267  
3 age                     -0.129    0.0687     -1.89    6.04e-2  -0.265  0.00567
4 factor(has_siblings)1   -0.380    0.157      -2.42    1.61e-2  -0.689 -0.0710 
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)         6.18       0.701      8.81  1.43e-16   4.80      7.56  
2 social_media_usage  0.00793    0.0335     0.237 8.13e- 1  -0.0579    0.0738
3 age                -0.111      0.0508    -2.18  2.99e- 2  -0.211    -0.0109
4 physical_activity  -0.471      0.0305   -15.4   3.79e-39  -0.531    -0.411 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)            6.14       0.704      8.72  2.65e-16   4.76      7.53  
2 social_media_usage     0.00634    0.0336     0.189 8.50e- 1  -0.0598    0.0724
3 age                   -0.111      0.0509    -2.18  2.98e- 2  -0.211    -0.0109
4 physical_activity     -0.476      0.0316   -15.1   7.62e-38  -0.538    -0.414 
5 factor(has_siblings)1  0.0784     0.120      0.653 5.14e- 1  -0.158     0.315 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 2 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          2.96      0.0719     41.2  4.98e-120   2.82       3.10 
2 social_media_usage   0.0966    0.0285      3.39 8.04e-  4   0.0405     0.153
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             3.24      0.135      24.0  1.15e-69   2.98      3.51  
2 social_media_usage      0.0964    0.0283      3.41 7.46e- 4   0.0407    0.152 
3 factor(has_siblings)1  -0.391     0.159      -2.46 1.45e- 2  -0.704    -0.0781
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic   p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>     <dbl>    <dbl>     <dbl>
1 (Intercept)          4.69      0.122     38.4   1.09e-112   4.45      4.93  
2 social_media_usage  -0.0188    0.0220    -0.853 3.94e-  1  -0.0622    0.0246
3 physical_activity   -0.479     0.0305   -15.7   4.31e- 40  -0.539    -0.419 
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic   p.value conf.low conf.h…¹
  <chr>                    <dbl>     <dbl>     <dbl>     <dbl>    <dbl>    <dbl>
1 (Intercept)             4.65      0.135     34.4   1.42e-101   4.39     4.92  
2 social_media_usage     -0.0201    0.0221    -0.908 3.65e-  1  -0.0637   0.0235
3 physical_activity      -0.484     0.0316   -15.3   9.32e- 39  -0.547   -0.422 
4 factor(has_siblings)1   0.0840    0.121      0.695 4.88e-  1  -0.154    0.322 
# … with abbreviated variable name ¹​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 3 × 7
  term               estimate std.error statistic    p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>      <dbl>    <dbl>     <dbl>
1 (Intercept)           4.59     0.954       4.81 0.00000254   2.71      6.46  
2 social_media_usage    0.107    0.0291      3.69 0.000273     0.0500    0.165 
3 age                  -0.119    0.0697     -1.71 0.0888      -0.256     0.0182
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term                  estimate std.error statistic     p.value conf.…¹ conf.…²
  <chr>                    <dbl>     <dbl>     <dbl>       <dbl>   <dbl>   <dbl>
1 (Intercept)              4.85     0.952       5.09 0.000000652  2.97    6.72  
2 social_media_usage       0.107    0.0288      3.71 0.000253     0.0501  0.164 
3 age                     -0.118    0.0691     -1.70 0.0894      -0.254   0.0182
4 factor(has_siblings)1   -0.389    0.158      -2.46 0.0147      -0.700  -0.0771
# … with abbreviated variable names ¹​conf.low, ²​conf.high
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 4 × 7
  term               estimate std.error statistic  p.value conf.low conf.high
  <chr>                 <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)         6.11       0.700      8.72  2.63e-16   4.73     7.49   
2 social_media_usage -0.00924    0.0224    -0.413 6.80e- 1  -0.0533   0.0349 
3 age                -0.104      0.0507    -2.05  4.12e- 2  -0.204   -0.00418
4 physical_activity  -0.478      0.0303   -15.7   3.12e-40  -0.537   -0.418  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results
# A tibble: 5 × 7
  term                  estimate std.error statistic  p.value conf.low conf.high
  <chr>                    <dbl>     <dbl>     <dbl>    <dbl>    <dbl>     <dbl>
1 (Intercept)             6.07      0.703      8.63  4.99e-16   4.69     7.45   
2 social_media_usage     -0.0105    0.0225    -0.469 6.40e- 1  -0.0548   0.0337 
3 age                    -0.104     0.0507    -2.05  4.12e- 2  -0.204   -0.00419
4 physical_activity      -0.483     0.0314   -15.4   6.63e-39  -0.545   -0.421  
5 factor(has_siblings)1   0.0847    0.120      0.705 4.81e- 1  -0.152    0.321  
model.results = broom::tidy(fit, conf.int = TRUE)
model.results

The estimated effect of social_media_usage on depression is shown in the figure below, along with other estimated coefficients. If the coefficient was negative, it would imply that increased social media usage is inversely associated with depression i.e. social media usage has a positive impact on mental well being; on the other hand if it is positive, it would imply that social media usage is positively associated with depression i.e. social media usage has a negative impact on mental well being. Finally, if the coefficient is very close to zero, it suggests that the the relationship is weak.

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
    filter(term != "(Intercept)") %>%
    ggplot() + geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
    geom_vline(aes(xintercept = 0)) + xlim(c(-2, 2)) + ylab("Modelcoefficients") +
    theme_minimal() + theme(axis.title.x = element_blank())

model.results %>%
  filter(term != "(Intercept)") %>%
  ggplot() +
  geom_pointrange(aes(y = term, x = estimate, xmin = conf.low, xmax = conf.high)) +
  geom_vline(aes(xintercept = 0)) +
  xlim(c(-2, 2)) +
  ylab("Model coefficients") +
  theme_minimal() +
  theme(
    axis.title.x = element_blank()
  )

From the variation in the result, as shown in Figure 1, the impact of social media usage on depression appears to vary based on which choices we make in the data analysis process. This is more evident from the specification curve plot (Figure 2) which shows the variation in the outcome, with only less than half the specifications suggesting a positive effect.

data.spec_curve = extract_variables(M, model.results) %>%
  unnest(model.results) %>%
  # filter(stringr::str_detect(term, "^I")) %>%
  filter(term == "social_media_usage") %>%
  select( .universe, !! names(parameters(M)), estimate, p.value, conf.low, conf.high ) %>%
  arrange( estimate ) %>%
  mutate( 
    .universe = 1:nrow(.),
    effect = ifelse(p.value < 0.05, ifelse(estimate < 0, "negative", "positive"), "not significant")
  )

p1 <- data.spec_curve %>%
  gather( "parameter_name", "parameter_option", !! names(parameters(M)) ) %>%
  mutate( parameter_name = factor(stringr::str_replace(parameter_name, "_", "\n"))  ) %>%
  ggplot() +
  geom_point( aes(x = .universe, y = parameter_option, color = effect), size = 1 ) +
  labs( x = "universe #", y = "option included in the analysis specification") + 
  facet_grid(parameter_name ~ ., space="free_y", scales="free_y", switch="y")+ 
  scale_colour_manual(values=c("#FF684B", "#999999", "#6E52EB")) +
  theme_minimal() +
  theme(strip.placement = "outside",
        strip.background = element_rect(fill=NA,colour=NA),
        panel.spacing.x=unit(0.15,"cm"), 
        strip.text.y = element_text(angle = 180, face="bold", size=10), 
        panel.spacing = unit(0.25, "lines")
      )

p2 <- data.spec_curve %>%
  ggplot() +
  ggdist::geom_pointinterval(aes(x = .universe, y = estimate, ymin = conf.low, ymax = conf.high, color = effect)) +
  labs(x = "", y = "effect size") + 
  theme_minimal() +
  scale_colour_manual(values=c("#FF684B", "#999999", "#6E52EB"))

cowplot::plot_grid(p2, p1, axis = "bltr",  align = "v", ncol = 1, rel_heights = c(1, 3))
## Warning: Using the `size` aesthietic with geom_segment was deprecated in ggplot2 3.4.0.
## ℹ Please use the `linewidth` aesthetic instead.

Conclusion

As a result, we conclude that the association between social media usage and depression is not robust to arbitrary choices in the data analysis process, and any impact that prior work has found on social media usage on depression is likely due to idiosyncratic choices in the data analysis process.